Compare commits

...

5 Commits

Author SHA1 Message Date
63b35414d2 fix: pgxpool context cancellation hang on Ctrl+C during cluster restore
Some checks failed
CI/CD / Test (push) Has been cancelled
CI/CD / Integration Tests (push) Has been cancelled
CI/CD / Native Engine Tests (push) Has been cancelled
CI/CD / Lint (push) Has been cancelled
CI/CD / Build Binary (push) Has been cancelled
CI/CD / Test Release Build (push) Has been cancelled
CI/CD / Release Binaries (push) Has been cancelled
- Fixed pgxpool created with context.Background() causing background health check goroutine to hang
- Added NewParallelRestoreEngineWithContext() to properly pass cancellable context
- Added context cancellation checks in parallel worker goroutines (Phase 3 COPY, Phase 4 indexes)
- Workers now exit cleanly when context is cancelled instead of continuing indefinitely

Version 5.8.7
2026-02-04 08:14:35 +01:00
db46770e7f v5.8.6: Support pg_dumpall SQL files in cluster restore
Some checks failed
CI/CD / Test (push) Successful in 2m59s
CI/CD / Lint (push) Successful in 1m10s
CI/CD / Integration Tests (push) Failing after 25s
CI/CD / Native Engine Tests (push) Successful in 50s
CI/CD / Build Binary (push) Successful in 44s
CI/CD / Test Release Build (push) Successful in 1m17s
CI/CD / Release Binaries (push) Failing after 10m7s
NEW FEATURE:
- TUI cluster restore now accepts .sql and .sql.gz files (pg_dumpall output)
- Uses native engine automatically for SQL-based cluster restores
- Added CanBeClusterRestore() method to detect valid cluster formats

Supported cluster restore formats:
- .tar.gz (dbbackup cluster format)
- .sql (pg_dumpall plain format)
- .sql.gz (pg_dumpall compressed format)
2026-02-03 22:38:32 +01:00
51764a677a v5.8.5: Improve cluster restore error message for pg_dumpall SQL files
Some checks failed
CI/CD / Integration Tests (push) Has been cancelled
CI/CD / Native Engine Tests (push) Has been cancelled
CI/CD / Lint (push) Has been cancelled
CI/CD / Build Binary (push) Has been cancelled
CI/CD / Test Release Build (push) Has been cancelled
CI/CD / Release Binaries (push) Has been cancelled
CI/CD / Test (push) Has been cancelled
- Better error message when selecting non-.tar.gz file in cluster restore
- Explains that pg_dumpall SQL files should be restored via: psql -f <file.sql>
- Shows actual psql command with correct host/port/user from config
2026-02-03 22:27:39 +01:00
bdbbb59e51 v5.8.4: Fix config file loading (was completely broken)
Some checks failed
CI/CD / Test (push) Has been cancelled
CI/CD / Integration Tests (push) Has been cancelled
CI/CD / Native Engine Tests (push) Has been cancelled
CI/CD / Lint (push) Has been cancelled
CI/CD / Build Binary (push) Has been cancelled
CI/CD / Test Release Build (push) Has been cancelled
CI/CD / Release Binaries (push) Has been cancelled
CRITICAL FIX:
- Config file loading was completely broken since v5.x
- A duplicate PersistentPreRunE was overwriting the config loading logic
- Now .dbbackup.conf and --config flag work correctly

The second PersistentPreRunE (for password deprecation) was replacing
the entire config loading logic, so no config files were ever loaded.
2026-02-03 22:11:31 +01:00
1a6ea13222 v5.8.3: Fix TUI cluster restore validation for non-tar.gz files
Some checks failed
CI/CD / Test (push) Has been cancelled
CI/CD / Integration Tests (push) Has been cancelled
CI/CD / Native Engine Tests (push) Has been cancelled
CI/CD / Lint (push) Has been cancelled
CI/CD / Build Binary (push) Has been cancelled
CI/CD / Test Release Build (push) Has been cancelled
CI/CD / Release Binaries (push) Has been cancelled
- Block selection of single DB backups (.sql, .dump) in cluster restore mode
- Show informative error message when wrong backup type selected
- Prevents misleading error at restore execution time
2026-02-03 22:02:55 +01:00
6 changed files with 156 additions and 26 deletions

View File

@ -15,11 +15,12 @@ import (
)
var (
cfg *config.Config
log logger.Logger
auditLogger *security.AuditLogger
rateLimiter *security.RateLimiter
notifyManager *notify.Manager
cfg *config.Config
log logger.Logger
auditLogger *security.AuditLogger
rateLimiter *security.RateLimiter
notifyManager *notify.Manager
deprecatedPassword string
)
// rootCmd represents the base command when called without any subcommands
@ -47,6 +48,11 @@ For help with specific commands, use: dbbackup [command] --help`,
return nil
}
// Check for deprecated password flag
if deprecatedPassword != "" {
return fmt.Errorf("--password flag is not supported for security reasons. Use environment variables instead:\n - MySQL/MariaDB: export MYSQL_PWD='your_password'\n - PostgreSQL: export PGPASSWORD='your_password' or use .pgpass file")
}
// Store which flags were explicitly set by user
flagsSet := make(map[string]bool)
cmd.Flags().Visit(func(f *pflag.Flag) {
@ -171,15 +177,8 @@ func Execute(ctx context.Context, config *config.Config, logger logger.Logger) e
rootCmd.PersistentFlags().StringVar(&cfg.Database, "database", cfg.Database, "Database name")
// SECURITY: Password flag removed - use PGPASSWORD/MYSQL_PWD environment variable or .pgpass file
// Provide helpful error message for users expecting --password flag
var deprecatedPassword string
rootCmd.PersistentFlags().StringVar(&deprecatedPassword, "password", "", "DEPRECATED: Use MYSQL_PWD or PGPASSWORD environment variable instead")
rootCmd.PersistentFlags().MarkHidden("password")
rootCmd.PersistentPreRunE = func(cmd *cobra.Command, args []string) error {
if deprecatedPassword != "" {
return fmt.Errorf("--password flag is not supported for security reasons. Use environment variables instead:\n - MySQL/MariaDB: export MYSQL_PWD='your_password'\n - PostgreSQL: export PGPASSWORD='your_password' or use .pgpass file")
}
return nil
}
rootCmd.PersistentFlags().StringVarP(&cfg.DatabaseType, "db-type", "d", cfg.DatabaseType, "Database type (postgres|mysql|mariadb)")
rootCmd.PersistentFlags().StringVar(&cfg.BackupDir, "backup-dir", cfg.BackupDir, "Backup directory")
rootCmd.PersistentFlags().BoolVar(&cfg.NoColor, "no-color", cfg.NoColor, "Disable colored output")

View File

@ -71,7 +71,14 @@ const (
)
// NewParallelRestoreEngine creates a new parallel restore engine
// NOTE: Pass a cancellable context to ensure the pool is properly closed on Ctrl+C
func NewParallelRestoreEngine(config *PostgreSQLNativeConfig, log logger.Logger, workers int) (*ParallelRestoreEngine, error) {
return NewParallelRestoreEngineWithContext(context.Background(), config, log, workers)
}
// NewParallelRestoreEngineWithContext creates a new parallel restore engine with context support
// This ensures the connection pool is properly closed when the context is cancelled
func NewParallelRestoreEngineWithContext(ctx context.Context, config *PostgreSQLNativeConfig, log logger.Logger, workers int) (*ParallelRestoreEngine, error) {
if workers < 1 {
workers = 4 // Default to 4 parallel workers
}
@ -94,7 +101,8 @@ func NewParallelRestoreEngine(config *PostgreSQLNativeConfig, log logger.Logger,
poolConfig.MaxConns = int32(workers + 2)
poolConfig.MinConns = int32(workers)
pool, err := pgxpool.NewWithConfig(context.Background(), poolConfig)
// Use the provided context so pool health checks stop when context is cancelled
pool, err := pgxpool.NewWithConfig(ctx, poolConfig)
if err != nil {
return nil, fmt.Errorf("failed to create connection pool: %w", err)
}
@ -215,17 +223,38 @@ func (e *ParallelRestoreEngine) RestoreFile(ctx context.Context, filePath string
semaphore := make(chan struct{}, options.Workers)
var completedCopies int64
var totalRows int64
var cancelled int32 // Atomic flag to signal cancellation
for _, stmt := range copyStmts {
// Check for context cancellation before starting new work
if ctx.Err() != nil {
break
}
wg.Add(1)
semaphore <- struct{}{} // Acquire worker slot
select {
case semaphore <- struct{}{}: // Acquire worker slot
case <-ctx.Done():
wg.Done()
atomic.StoreInt32(&cancelled, 1)
break
}
go func(s *SQLStatement) {
defer wg.Done()
defer func() { <-semaphore }() // Release worker slot
// Check cancellation before executing
if ctx.Err() != nil || atomic.LoadInt32(&cancelled) == 1 {
return
}
rows, err := e.executeCopy(ctx, s)
if err != nil {
if ctx.Err() != nil {
// Context cancelled, don't log as error
return
}
if options.ContinueOnError {
e.log.Warn("COPY failed", "table", s.TableName, "error", err)
} else {
@ -243,6 +272,12 @@ func (e *ParallelRestoreEngine) RestoreFile(ctx context.Context, filePath string
}
wg.Wait()
// Check if cancelled
if ctx.Err() != nil {
return result, ctx.Err()
}
result.TablesRestored = completedCopies
result.RowsRestored = totalRows
@ -264,15 +299,35 @@ func (e *ParallelRestoreEngine) RestoreFile(ctx context.Context, filePath string
// Execute post-data in parallel
var completedPostData int64
cancelled = 0 // Reset for phase 4
for _, sql := range postDataStmts {
// Check for context cancellation before starting new work
if ctx.Err() != nil {
break
}
wg.Add(1)
semaphore <- struct{}{}
select {
case semaphore <- struct{}{}:
case <-ctx.Done():
wg.Done()
atomic.StoreInt32(&cancelled, 1)
break
}
go func(stmt string) {
defer wg.Done()
defer func() { <-semaphore }()
// Check cancellation before executing
if ctx.Err() != nil || atomic.LoadInt32(&cancelled) == 1 {
return
}
if err := e.executeStatement(ctx, stmt); err != nil {
if ctx.Err() != nil {
return // Context cancelled
}
if options.ContinueOnError {
e.log.Warn("Post-data statement failed", "error", err)
}
@ -289,6 +344,11 @@ func (e *ParallelRestoreEngine) RestoreFile(ctx context.Context, filePath string
wg.Wait()
// Check if cancelled
if ctx.Err() != nil {
return result, ctx.Err()
}
result.Duration = time.Since(startTime)
e.log.Info("Parallel restore completed",
"duration", result.Duration,

View File

@ -635,7 +635,8 @@ func (e *Engine) restoreWithNativeEngine(ctx context.Context, archivePath, targe
"database", targetDB,
"archive", archivePath)
parallelEngine, err := native.NewParallelRestoreEngine(nativeCfg, e.log, parallelWorkers)
// Pass context to ensure pool is properly closed on Ctrl+C cancellation
parallelEngine, err := native.NewParallelRestoreEngineWithContext(ctx, nativeCfg, e.log, parallelWorkers)
if err != nil {
e.log.Warn("Failed to create parallel restore engine, falling back to sequential", "error", err)
// Fall back to sequential restore
@ -1342,9 +1343,14 @@ func (e *Engine) RestoreCluster(ctx context.Context, archivePath string, preExtr
}
format := DetectArchiveFormat(archivePath)
if format != FormatClusterTarGz {
if !format.CanBeClusterRestore() {
operation.Fail("Invalid cluster archive format")
return fmt.Errorf("not a cluster archive: %s (detected format: %s)", archivePath, format)
return fmt.Errorf("not a valid cluster restore format: %s (detected format: %s). Supported: .tar.gz, .sql, .sql.gz", archivePath, format)
}
// For SQL-based cluster restores, use a different restore path
if format == FormatPostgreSQLSQL || format == FormatPostgreSQLSQLGz {
return e.restoreClusterFromSQL(ctx, archivePath, operation)
}
// Check if we have a pre-extracted directory (optimization to avoid double extraction)
@ -2177,6 +2183,45 @@ func (e *Engine) RestoreCluster(ctx context.Context, archivePath string, preExtr
return nil
}
// restoreClusterFromSQL restores a pg_dumpall SQL file using the native engine
// This handles .sql and .sql.gz files containing full cluster dumps
func (e *Engine) restoreClusterFromSQL(ctx context.Context, archivePath string, operation logger.OperationLogger) error {
e.log.Info("Restoring cluster from SQL file (pg_dumpall format)",
"file", filepath.Base(archivePath),
"native_engine", true)
clusterStartTime := time.Now()
// Determine if compressed
compressed := strings.HasSuffix(strings.ToLower(archivePath), ".gz")
// Use native engine to restore directly to postgres database (globals + all databases)
e.log.Info("Restoring SQL dump using native engine...",
"compressed", compressed,
"size", FormatBytes(getFileSize(archivePath)))
e.progress.Start("Restoring cluster from SQL dump...")
// For pg_dumpall, we restore to the 'postgres' database which then creates other databases
targetDB := "postgres"
err := e.restoreWithNativeEngine(ctx, archivePath, targetDB, compressed)
if err != nil {
operation.Fail(fmt.Sprintf("SQL cluster restore failed: %v", err))
e.recordClusterRestoreMetrics(clusterStartTime, archivePath, 0, 0, false, err.Error())
return fmt.Errorf("SQL cluster restore failed: %w", err)
}
duration := time.Since(clusterStartTime)
e.progress.Complete(fmt.Sprintf("Cluster restored successfully from SQL in %s", duration.Round(time.Second)))
operation.Complete("SQL cluster restore completed")
// Record metrics
e.recordClusterRestoreMetrics(clusterStartTime, archivePath, 1, 1, true, "")
return nil
}
// recordClusterRestoreMetrics records metrics for cluster restore operations
func (e *Engine) recordClusterRestoreMetrics(startTime time.Time, archivePath string, totalDBs, successCount int, success bool, errorMsg string) {
duration := time.Since(startTime)
@ -2924,6 +2969,15 @@ func (e *Engine) isIgnorableError(errorMsg string) bool {
return false
}
// getFileSize returns the size of a file, or 0 if it can't be read
func getFileSize(path string) int64 {
info, err := os.Stat(path)
if err != nil {
return 0
}
return info.Size()
}
// FormatBytes formats bytes to human readable format
func FormatBytes(bytes int64) string {
const unit = 1024

View File

@ -168,11 +168,19 @@ func (f ArchiveFormat) IsCompressed() bool {
f == FormatClusterTarGz
}
// IsClusterBackup returns true if the archive is a cluster backup
// IsClusterBackup returns true if the archive is a cluster backup (.tar.gz format created by dbbackup)
func (f ArchiveFormat) IsClusterBackup() bool {
return f == FormatClusterTarGz
}
// CanBeClusterRestore returns true if the format can be used for cluster restore
// This includes .tar.gz (dbbackup format) and .sql/.sql.gz (pg_dumpall format for native engine)
func (f ArchiveFormat) CanBeClusterRestore() bool {
return f == FormatClusterTarGz ||
f == FormatPostgreSQLSQL ||
f == FormatPostgreSQLSQLGz
}
// IsPostgreSQL returns true if the archive is PostgreSQL format
func (f ArchiveFormat) IsPostgreSQL() bool {
return f == FormatPostgreSQLDump ||

View File

@ -205,11 +205,20 @@ func (m ArchiveBrowserModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
return diagnoseView, diagnoseView.Init()
}
// For restore-cluster mode:
// - .tar.gz cluster archives → full cluster restore
// - .sql/.sql.gz files → single database restore (Native Engine supports these)
// - .dump/.dump.gz → single database restore (pg_restore)
// ALL formats are now allowed for restore operations!
// For restore-cluster mode: check if format can be used for cluster restore
// - .tar.gz: dbbackup cluster format (works with pg_restore)
// - .sql/.sql.gz: pg_dumpall format (works with native engine or psql)
if m.mode == "restore-cluster" && !selected.Format.CanBeClusterRestore() {
m.message = errorStyle.Render(fmt.Sprintf("⚠️ %s cannot be used for cluster restore.\n\n Supported formats: .tar.gz (dbbackup), .sql, .sql.gz (pg_dumpall)",
selected.Name))
return m, nil
}
// For SQL-based cluster restore, enable native engine automatically
if m.mode == "restore-cluster" && !selected.Format.IsClusterBackup() {
// This is a .sql or .sql.gz file - use native engine
m.config.UseNativeEngine = true
}
// For single restore mode with cluster backup selected - offer to select individual database
if m.mode == "restore-single" && selected.Format.IsClusterBackup() {
@ -217,7 +226,7 @@ func (m ArchiveBrowserModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
return clusterSelector, clusterSelector.Init()
}
// Open restore preview for any valid format
// Open restore preview for valid format
preview := NewRestorePreview(m.config, m.logger, m.parent, m.ctx, selected, m.mode)
return preview, preview.Init()
}

View File

@ -16,7 +16,7 @@ import (
// Build information (set by ldflags)
var (
version = "5.8.2"
version = "5.8.7"
buildTime = "unknown"
gitCommit = "unknown"
)